Search Results for author:
Found 35 papers, 3 papers with code
Jointly learning visual motion and confidence from local patches in event cameras
In the task of recovering pan-tilt ego velocities from events, we show that each individual confident local prediction of our network can be expected to be as accurate as state of the art optimization approaches which utilize the full image.
FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection
While ControlNet provides control over the geometric form of the instances in the generated image, it lacks the capability to dictate the visual appearance of each instance.
VioLA: Aligning Videos to 2D LiDAR Scans
We study the problem of aligning a video that captures a local portion of an environment to the 2D LiDAR scan of the entire environment.
HIO-SDF: Hierarchical Incremental Online Signed Distance Fields
HIO-SDF combines the advantages of these representations using a hierarchical approach which employs a coarse voxel grid that captures the observed parts of the environment together with high-resolution local information to train a neural network.
HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image
The inference as well as training-data generation for 3D hand-object scene reconstruction is challenging due to the depth ambiguity of a single image and occlusions by the hand and object.
RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
General scene reconstruction refers to the task of estimating the full 3D geometry and texture of a scene containing previously unseen objects.
Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp Prediction
In this paper, we present a novel method to provide this geometric and semantic information of all objects in the scene as well as feasible grasps on those objects simultaneously.
EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers.
3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data
In this work, we present a new method for joint category-specific 3D reconstruction and object pose estimation from a single image.
Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences
This paper proposes an optimization method that retains all possible correspondences for each keypoint when matching a partial point cloud to a complete point cloud.
Self-supervised Wide Baseline Visual Servoing via 3D Equivariance
Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes.
Apple Counting using Convolutional Neural Networks
Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention.
PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound
Based on this insight, we introduce a time-invariant transfer function called pose kernel -- the impulse response of audio signals induced by the body pose.
Learning Continuous Cost-to-Go Functions for Non-holonomic Systems
In this work, we show that uniform sampling fails for non-holonomic systems.
Ellipse Regression with Predicted Uncertainties for Accurate Multi-View 3D Object Estimation
We present a novel ellipse regression loss which can learn the offset parameters with their uncertainties and quantify the overall geometric quality of detection for each ellipse.
Cost-to-Go Function Generating Networks for High Dimensional Motion Planning
The c2g-HOF architecture consists of a cost-to-go function over the configuration space represented as a neural network (c2g-network) as well as a Higher Order Function (HOF) network which outputs the weights of the c2g-network for a given input workspace.
Fast Motion Understanding with Spatiotemporal Neural Networks and Dynamic Vision Sensors
This paper presents a Dynamic Vision Sensor (DVS) based system for reasoning about high speed motion.
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
As a result, current approaches typically rely on supervised training with either ground truth 3D models or multiple target images.
Geodesic-HOF: 3D Reconstruction Without Cutting Corners
To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance on the object.
Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection
This paper presents a novel end-to-end system for pedestrian detection using Dynamic Vision Sensors (DVSs).
Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction
We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network.
Robotics
Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion
We first propose a robust and compact ellipse regression based on the Mask R-CNN architecture for elliptical object detection.
Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks
Our approach is to learn a Higher Order Function (HOF) which takes an image of an object as input and generates a mapping function.
QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning
The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks.
Higher Order Function Networks for View Planning and Multi-View Reconstruction
In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects.
MinneApple: A Benchmark Dataset for Apple Detection and Segmentation
The fruits are labeled using polygonal masks for each object instance to aid in precise object detection, localization, and segmentation.
Higher-Order Function Networks for Learning Composable 3D Object Representations
We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network.
Semantics-Aware Image to Image Translation and Domain Transfer
Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain.
A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards
We present new methods for apple detection and counting based on recent deep learning approaches and compare them with state-of-the-art results based on classical methods.
Semantic Mapping for Orchard Environments by Merging Two-Sides Reconstructions of Tree Rows
Our first main contribution in this paper is a novel method that utilizes global features and semantic information to obtain an initial solution aligning the two sides.
Robotics
Vision-Based Preharvest Yield Mapping for Apple Orchards
Additionally, we report merged fruit counts from both sides of the tree rows.
Adaptive View Planning for Aerial 3D Reconstruction
We then present (i)~a method that builds a view manifold for view selection, and (ii) an algorithm to select a sparse set of views.
Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments
Researchers often rely on manual measurements which may not be accurate for example when measuring tree volume.
View Selection with Geometric Uncertainty Modeling
Consider a world point $g \in \mathcal{G}$ and its worst case reconstruction uncertainty $\varepsilon(g,\mathcal{S})$ obtained by merging \emph{all} possible views of $g$ chosen from $\mathcal{S}$.
A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera
We present a novel method for extrinsically calibrating a camera and a 2D Laser Rangefinder (LRF) whose beams are invisible from the camera image.
